Re: [PATCH mm-unstable v1 2/3] mm/cma: add cma_alloc_folio()

[Kefeng Wang <wangkefeng.wang@huawei.com>]

On 2024/8/12 5:21, Yu Zhao wrote:
> With alloc_contig_range() and free_contig_range() supporting large
> folios, CMA can allocate and free large folios too, by
> cma_alloc_folio() and cma_release().
> 
> Signed-off-by: Yu Zhao <yuzhao@google.com>
> ---
>   include/linux/cma.h |  1 +
>   mm/cma.c            | 47 ++++++++++++++++++++++++++++++---------------
>   2 files changed, 33 insertions(+), 15 deletions(-)
> 
> diff --git a/include/linux/cma.h b/include/linux/cma.h
> index 9db877506ea8..086553fbda73 100644
> --- a/include/linux/cma.h
> +++ b/include/linux/cma.h
> @@ -46,6 +46,7 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
>   					struct cma **res_cma);
>   extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align,
>   			      bool no_warn);
> +extern struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp);
>   extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count);
>   extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count);
>   
> diff --git a/mm/cma.c b/mm/cma.c
> index 95d6950e177b..46feb06db8e7 100644
> --- a/mm/cma.c
> +++ b/mm/cma.c
> @@ -403,18 +403,8 @@ static void cma_debug_show_areas(struct cma *cma)
>   	spin_unlock_irq(&cma->lock);
>   }
>   
> -/**
> - * cma_alloc() - allocate pages from contiguous area
> - * @cma:   Contiguous memory region for which the allocation is performed.
> - * @count: Requested number of pages.
> - * @align: Requested alignment of pages (in PAGE_SIZE order).
> - * @no_warn: Avoid printing message about failed allocation
> - *
> - * This function allocates part of contiguous memory on specific
> - * contiguous memory area.
> - */
> -struct page *cma_alloc(struct cma *cma, unsigned long count,
> -		       unsigned int align, bool no_warn)
> +static struct page *__cma_alloc(struct cma *cma, unsigned long count,
> +				unsigned int align, gfp_t gfp)
>   {
>   	unsigned long mask, offset;
>   	unsigned long pfn = -1;
> @@ -463,8 +453,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
>   
>   		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
>   		mutex_lock(&cma_mutex);
> -		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA,
> -				     GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0));
> +		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, gfp);
>   		mutex_unlock(&cma_mutex);
>   		if (ret == 0) {
>   			page = pfn_to_page(pfn);
> @@ -494,7 +483,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
>   			page_kasan_tag_reset(nth_page(page, i));
>   	}
>   
> -	if (ret && !no_warn) {
> +	if (ret && !(gfp & __GFP_NOWARN)) {
>   		pr_err_ratelimited("%s: %s: alloc failed, req-size: %lu pages, ret: %d\n",
>   				   __func__, cma->name, count, ret);
>   		cma_debug_show_areas(cma);
> @@ -513,6 +502,34 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
>   	return page;
>   }
>   
> +/**
> + * cma_alloc() - allocate pages from contiguous area
> + * @cma:   Contiguous memory region for which the allocation is performed.
> + * @count: Requested number of pages.
> + * @align: Requested alignment of pages (in PAGE_SIZE order).
> + * @no_warn: Avoid printing message about failed allocation
> + *
> + * This function allocates part of contiguous memory on specific
> + * contiguous memory area.
> + */
> +struct page *cma_alloc(struct cma *cma, unsigned long count,
> +		       unsigned int align, bool no_warn)
> +{
> +	return __cma_alloc(cma, count, align, GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0));
> +}
> +
> +struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp)
> +{
> +	struct page *page;
> +
> +	if (WARN_ON(order && !(gfp | __GFP_COMP)))
> +		return NULL;
> +
> +	page = __cma_alloc(cma, 1 << order, order, gfp);
> +
> +	return page ? page_folio(page) : NULL;

We don't set large_rmappable for cma alloc folio, which is not consistent
with  other folio allocation, eg  folio_alloc/folio_alloc_mpol(),
there is no issue for HugeTLB folio, and for HugeTLB folio must without
large_rmappable, but once we use it for mTHP/THP, it need some extra
handle, maybe we set large_rmappable here, and clear it in
init_new_hugetlb_folio()?

> +}
> +
>   bool cma_pages_valid(struct cma *cma, const struct page *pages,
>   		     unsigned long count)
>   {